We ran Octokraft (code health platform) on 24 open source projects. 14 heritage repos like Kubernetes, Django, Terraform and 10 AI-heavy ones like Supabase, cal.com, n8n.
Both groups have issues, but they look different. Heritage repos show accumulated coordination burden: protocol evolution, config hubs, large controllers, years of backfilled responsibilities.
AI-heavy repos show initial over-aggregation: one adapter, one dataloader, one plugin file with too many methods. AI-heavy projects also had about 2x the testing issue density.
I built octokraft.com for this and have been using it on all my projects, so far it's been going well, I can immediately see when things go off-rails and tell my agents to fix them
I'm building something that I called control plane for agents, but it's only solving half of the problem you're mentioning. Basically it allows me to connect to my agents remotely from anywhere, so I have one running on my server and several running on my home PC. I generally just use something like notion or beads for issue tracking.
Another thing I do is I have a custom Claude skill that runs every night and goes through all my repositories and Claude conversations and then updates my dashboard and tasks in notion with progress.
Both groups have issues, but they look different. Heritage repos show accumulated coordination burden: protocol evolution, config hubs, large controllers, years of backfilled responsibilities. AI-heavy repos show initial over-aggregation: one adapter, one dataloader, one plugin file with too many methods. AI-heavy projects also had about 2x the testing issue density.
You can explore the full analysis of all the projects in the showcase at https://app.octokraft.com/showcase/BENCHMA785